Sofie Lövdal

According to our database, Sofie Lövdal authored at least 7 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Iterated relevance matrix analysis for improved classification and robustness in prototype-based learning schemes.

Sofie Lövdal, Elina L. van den Brandhof, Michael Biehl

Neurocomputing, 2026

FA(IR)2MA-GLVQ - A hidden-feature-bias mitigation approach for fairness in classification learning based on generalized matrix learning vector quantization.

Marika Kaden, Ronny Schubert, Julius Voigt, Lynn V. Reuss, Alexander Engelsberger, Sofie Lövdal, Elina L. van den Brandhof, Michael Biehl, Thomas Villmann

Neurocomputing, 2026

Autoencoders versus PCA for feature extraction in FDG PET scans in neurodegenerative diseases.

Roland J. Veen, Sofie Lövdal, Kaitlin Vos, Ciro Setolino, Sanne K. Meles, Michael Biehl

Proceedings of the 34th European Symposium on Artificial Neural Networks, 2026

2025

Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach - FA(IR)$^2$MA-GLVQ.

Marika Kaden, Alexander Engelsberger, Ronny Schubert, Sofie Lövdal, Elina L. van den Brandhof, Michael Biehl, Thomas Villmann

Proceedings of the 33rd European Symposium on Artificial Neural Networks, 2025

2024

Iterated Relevance Matrix Analysis (IRMA) for the identification of class-discriminative subspaces.

Sofie Lövdal, Michael Biehl

Neurocomputing, 2024

Subspace corrected relevance learning with application in neuroimaging.

Rick van Veen, Neha Rajendra Bari Tamboli, Sofie Lövdal, Sanne K. Meles, Remco J. Renken, Gert-Jan de Vries, Dario Arnaldi, Silvia Morbelli, Pedro Clavero, José A. Obeso, Maria C. Rodriguez-Oroz, Klaus Leonard Leenders, Thomas Villmann, Michael Biehl

Artif. Intell. Medicine, 2024

2023

Improved Interpretation of Feature Relevances: Iterated Relevance Matrix Analysis (IRMA).

Michael Biehl, Sofie Lövdal

Proceedings of the 31st European Symposium on Artificial Neural Networks, 2023